Zhenxin Ai
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Crypto×1AI×1
Frequent co-authors
Research Timeline
2026
PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks
PASA introduces a robust, semantic-level watermarking technique that embeds and detects watermarks in the latent embedding space, successfully resisting semantic-invariant attacks like paraphrasing.
Highlighted terms show continued research focus across papers